© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18158
    Prev
    Next
    INDEX
    Explanations

    AI personalities, learned behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сову
    0.52
    язви
    0.48
    ForSettings
    0.47
    𒋛
    0.44
    uaje
    0.44
    थरूम
    0.44
    ังหวัด
    0.41
    惊讶
    0.41
     кнопку
    0.41
    arati
    0.40
    POSITIVE LOGITS
    ',
    0.45
    ,
    0.42
     and
    0.41
     relentless
    0.41
     formerly
    0.40
    （
    0.40
     একটা
    0.40
     telah
    0.40
     đã
    0.39
     insp
    0.39
    Activations Density 0.012%

    No Known Activations